Domenetap, at norsk blir erstattet av engelsk innenfor et spesielt område, er ofte sett på som en av de store truslene mot den norske språkutviklingen. De klassiske eksemplene på dette er transnasjonale selskaper som tar i bruk engelsk på arbeidsplassen, og innenfor utdanningssektoren hvor f.eks. høyere utdanning foregår på engelsk.
[W]hy would a party […] invest in oversight activities? The reason […] is that an opposition party will pursue electoral and office goals, and these goals can be achieved through engaging in executive oversight. Whitaker and Martin (2021)
Vi snakker her om foreldre, altså mødre og fedre, som ønsker å delta i sine barns aktiviteter, som f.eks. en fotballturnering. Du kan ikke komme deg fra Ålgård til Kverneland, det går ikke buss
# Loading packageslibrary(readr) # Read data through C++library(dplyr) # Parse manipulation of data through C++library(quanteda) # Manipulate text datalibrary(tidytext) # Structure text through C++library(tonR) # Some functions for reading Talk of Norway CoNLL-datalibrary(pbmcapply) # Parallelization with progress barlibrary(stringr)# Reading the main frame of ToNmeta <-read_csv("../../../gitDebates/talk-of-norway/data/ton_updated.csv", progress =TRUE)com <-pbmclapply(1:nrow(meta), function(x){# Extrating committee membershipdata.frame(com_member =unlist(strsplit(meta$com_member[x], " ; ")),com_date =unlist(strsplit(meta$com_date[x], " ; ")),com_role =unlist(strsplit(meta$com_role[x], " ; ")),date = meta$date[x],stringsAsFactors =FALSE)}, mc.cores =detectCores()-1)# Seting id on the speechesnames(com) <- meta$id# Binding all rowscom <-do.call(rbind, com)# Fixing id namescom$id <-gsub("\\.(.*?)$", "", rownames(com))# Making start and end date variables for committee membershipcom$date <-as.Date(com$date)com$com_start <-as.Date(str_split(com$com_date, " - ", n =2, simplify =TRUE)[, 1], format ="%d.%m.%Y")com$com_end <-as.Date(str_split(com$com_date, " - ", n =2, simplify =TRUE)[, 2], format ="%d.%m.%Y")com$com_check <-ifelse(com$com_start < com$date & com$com_end > com$date, "yes", "no")# Removing rows with committee membership that was not active at the time of the speechcom <- com[which(com$com_check !="no"), ]com$com_role2 <-factor(com$com_role,levels =rev(c("Stortingets president", "Stortingets visepresident og forsvarskomiteens leder","Leder", "Forsvarskomiteens leder", "Fung. leder gruppestyret","Nestleder", "Sekretær", "Første nestleder", "Andre nestleder","Medlem", "Varamedlem", "Personlig varamedlem")))com <- com |>group_by(id) |>summarize(high_com = com_member[which.max(com_role2)],com_role = com_role2[which.max(com_role2)])# Making dummy sets for all committee membershipsfor(i inunique(com$high_com)){ com[, tolower(gsub(" |[[:punct:]]", "", i))] <-ifelse(com$high_com == i, 1, 0)}# Aggregating to speech levelcom <- com |>group_by(id, com_role) |>summarize_at(vars(matches("komit")), sum)# Merging with original datameta <-merge(x = meta, y = com, by =c("id"), all.x =TRUE)# Subsetting the data to usemeta <- meta |>filter(is.na(party_id) ==FALSE&is.na(county) ==FALSE&is.na(session) ==FALSE) |># Excludes rows with missing on party_id, county, and sessionfilter(speaker_role =="Representant") |># Subsetting only representativesfilter(session =="2013-2014"| session =="2014-2015") |># Subsetting the two relevant sessionsfilter_at(vars(matches("komit")), any_vars(is.na(.) ==FALSE))meta$com_role <- meta$com_role.ymeta$com_role.y <-NULLmeta$com_role.x <-NULLmeta$com_role <-ifelse(meta$com_role =="Varamedlem", "Medlem", as.character(meta$com_role))# Reading the CoNLL-files for the remaining datalemmas_all <-pbmclapply(meta$id, function(x){read.conll("../../../gitDebates/talk-of-norway/", x)}, mc.cores =detectCores()-1, ignore.interactive =TRUE)# From list to data framelemmas_all <-bind_rows(lemmas_all)# Manipulating the textlemmas_all <- lemmas_all |>filter(grepl("[[:punct:]]|\\–|^AV$", lemma) ==FALSE) |># Removing "AV" because of tagger fail (not important as it is a stopword)group_by(id, sentence) |>mutate(lemma =tolower(lemma), # Lowercasing all lemmalemma =ifelse(lemma %in%stopwords("norwegian"), NA, lemma), # Removing stopwordslemma_pos =paste(lemma, part_of_speech, sep =":"),next_lemma_pos =lead(lemma_pos), # Leading lemma for bigram constructionlemma_pos_bigram =ifelse(grepl("^NA\\:|\\:NA$", lemma_pos) |grepl("^NA\\:|\\:NA$", next_lemma_pos), # Constructing bibramsNA, paste(lemma_pos, next_lemma_pos)),lemma_pos =ifelse(grepl("^NA\\:|\\:NA$", lemma_pos), NA, lemma_pos)) |>filter((is.na(lemma_pos) ==FALSE|is.na(lemma_pos_bigram) ==FALSE))lemmas_all <- lemmas_all |>mutate(lemma_pos_bigram =ifelse(grepl("\\sNA$", lemma_pos_bigram) ==FALSE, lemma_pos_bigram, NA)) |>filter(is.na(lemma_pos) ==FALSE|is.na(lemma_pos_bigram) ==FALSE)# Counting lemma bigramslemma_unigrams_pos <- lemmas_all |>filter(is.na(lemma_pos) ==FALSE) |>group_by(id) |>count(lemma_pos)# Counting lemma bigramslemma_bigrams_pos <- lemmas_all |>filter(is.na(lemma_pos_bigram) ==FALSE) |>group_by(id) |>count(lemma_pos_bigram)names(lemma_bigrams_pos)[2] <-"lemma_pos"lemma_counts <-bind_rows(lemma_unigrams_pos, lemma_bigrams_pos) |>filter(is.na(lemma_pos) ==FALSE) |># Removing if lemma is NAgroup_by(id) |># Grouping by speechfilter(length(lemma_pos) >=20) |># Removing speeches shorter than 20 lemmascount(lemma_pos) |># Counting the occurance of each lemma in each groupcast_dfm(id, lemma_pos, nn) |># Casting to document frequency matrixdfm_trim(min_docfreq =20, min_termfreq =5) # Trimming dfm to only contain speeches with more than 19 lemmas and# lemmas that occur more than 4 times across all documents# Subsetting the speeches that remain in the meta datameta <- meta[which(meta$id %in% lemma_counts@Dimnames[[1]]), ]# Removing redundant objectsrm(lemmas_all, lemma_bigrams_pos, lemma_unigrams_pos, i, com)# Saving the R-environmentsave.image(file ="./data/preprocess/reps_preproc_bigram_pos_com.rda")
Barnes, Jeremy, Samia Touileb, Lilja Øvrelid, and Erik Velldal. 2019. “Lexicon Information in Neural Sentiment Analysis: A Multi-Task Learning Approach.” In Proceedings of the 22nd Nordic Conference on Computational Linguistics, 175–86. Turku, Finland: Linköping University Electronic Press. https://aclanthology.org/W19-6119.
Bjørkholt, Solveig, and Martin Søyland. 2022. “Party Conflict and Coalition Control in Parliament.”
Finseraas, Henning, Bjørn Høyland, and Martin G. Søyland. 2021. “Climate Politics in Hard Times: How Local Economic Shocks Influence MPs Attention to Climate Change.”European Journal of Political Research 60 (3): 738–47. https://ejpr.onlinelibrary.wiley.com/doi/abs/10.1111/1475-6765.12415.
Gilardi, Fabrizio, and Bruno Wüest. 2018. “Text-as-Data Methods for Comparative Policy Analysis.”
Lapponi, Emanuele, Martin G. Søyland, Erik Velldal, and Stephan Oepen. 2018. “The Talk of Norway: A Richly Annotated Corpus of the Norwegian Parliament, 1998–2016.”Language Resources and Evaluation 52 (3): 873–93.
Søyland, Martin. 2022. “Party Control and Responsiveness: How MPs Use Variation in Lower-Level Institutional Design as an ElectoralResponsiveness Mechanism.”Digital Parliamentary Data in Action (DiPaDA 2022) Workshop, Uppsala, Sweden, March 15, 2022, CEUR-WS.org, Online. http://ceur-ws.org/Vol-3133/paper07.pdf.
Whitaker, Richard, and Shane Martin. 2021. “Divide to Conquer? Strategic Parliamentary Opposition and Coalition Government.”Party Politics.
